© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15540
    Prev
    Next
    INDEX
    Explanations

    "is something similar to this"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĦıæĢĿ
    -0.08
    oggle
    -0.08
    лаÑĤÑĭ
    -0.08
     bras
    -0.08
    ourd
    -0.08
    dbg
    -0.08
    ãģĬãĤĤ
    -0.08
    eway
    -0.07
    еÑģÑĤа
    -0.07
    roadcast
    -0.07
    POSITIVE LOGITS
     ÙħÙĤ
    0.06
     ries
    0.06
    å¡ŀ
    0.06
    _locked
    0.06
    追
    0.06
     Münster
    0.06
    alang
    0.06
    aln
    0.06
    æįIJ
    0.05
    _FUNCTION
    0.05
    Activations Density 0.012%

    No Known Activations